SelectiveDPO
Collection
Released models trained by Selective DPO.
•
6 items
•
Updated
This model is fine-tuned from the princeton-nlp/Llama-3-Base-8B-SFT model using the SelectiveDPO on the Ultrafeedback_binarized dataset.
For the recipe to reproduce this model, please visit our GitHub page.
- Downloads last month
- -
Model tree for glorgao/SelectiveDPO-Llama3-8B-SFT-UFBinarized
Base model
princeton-nlp/Llama-3-Base-8B-SFT